Advances in robust signal processing and applications

Thumbnail Image

Files

isbn9789526428789.pdf (1.23 MB)

URL

Journal Title

Journal ISSN

Volume Title

School of Electrical Engineering | Doctoral thesis (article-based) | Defence date: 2026-12-19
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.

Authors

Date

2025

Department

Informaatio- ja tietoliikennetekniikan laitos
Department of Information and Communications Engineering

Major/Subject

Mcode

Degree programme

Language

en

Pages

86 + app. 73

Series

Aalto University publication series Doctoral Theses, 249/2025

Abstract

Robust signal processing and machine learning methodologies are critical for the reliable operation of modern technological systems, particularly in dynamic and uncertain environments such as the Internet of Things (IoT). However, system performance is often compromised by pervasive challenges, including structural perturbations in graph-based models, complex non-Gaussian noise in communication systems, and the structural heterogeneity of high-dimensional tensor data. This thesis addresses these critical challenges by developing a suite of robust methodologies grounded in distinct yet complementary perspectives on robustness. First, this research establishes a comprehensive analytical framework to quantify the sensitivity of Graph Convolutional Neural Networks (GCNNs) to probabilistic graph perturbations. Tight, expected bounds for Graph Shift Operator (GSO) errors are derived without requiring eigendecomposition, and a linear relationship between GSO perturbations and GCNN output differences is revealed, providing theoretical stability guarantees for multilayer architectures. Second, novel robust device activity detection (AD) algorithms are developed for massive random access systems operating under challenging non-Gaussian noise. By formulating AD objectives based on robust loss functions (e.g., Huber's loss) and proving the geodesic convexity of the conditional objective, efficient fixed-point, coordinate-wise, and matching pursuit algorithms with proven convergence are proposed. These methods significantly outperform traditional Gaussianbased approaches in heavy-tailed noise environments. Third, a generalized Nonnegative Structured Kruskal Tensor Regression (NS-KTR) framework is introduced for the effective and interpretable modeling of high-dimensional tensor data. This framework integrates non-negativity constraints with mode-specific hybrid regularizations (e.g., LASSO, total variation, ridge), accommodates both linear and logistic regression, and is solved via an efficient ADMM-based algorithm. Collectively, this thesis advances the theory and practice of robust signal processing by providing novel tools for ensuring stability, resilience to distributional deviations, and robust modeling through structural priors. The developed frameworks and algorithms contribute to the design of more reliable and efficient signal processing systems for real-world applications.

Description

Supervising professor

Ollila, Esa, Prof., Aalto University, Department of Information and Communications Engineering, Finland

Thesis advisor

Vorobyov, Sergiy A., Prof., Aalto University, Department of Information and Communications Engineering, Finland

Keywords

robust signal processing, graph convolutional neural networks, massive machine-type communications, activity detection, tensor decomposition

Other note

Parts

  • [Publication 1]: X. Wang, E. Ollila, and S. A. Vorobyov. Graph neural network sensitivity under probabilistic error model. In Proc. 30th European Signal Processing Conference (EUSIPCO), Belgrade, Serbia, pp. 2146– 2150, August 2022.
    Full text in Acris/Aaltodoc: https://urn.fi/URN:NBN:fi:aalto-202211236547
  • [Publication 2]: X. Wang, E. Ollila, and S. A. Vorobyov. Graph convolutional neural networks sensitivity under probabilistic error model. IEEE Transactions on Signal and Information Processing over Networks, vol. 10, pp. 788-803, October 2024.
    Full text in Acris/Aaltodoc: https://urn.fi/URN:NBN:fi:aalto-202411267457
    DOI: 10.1109/TSIPN.2024.3485532 View at publisher
  • [Publication 3]: X.Wang, E. Ollila, S. A. Vorobyov. Robust activity detection for massive access using covariance-based matching pursuit. In Proc. 50th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, pp. 1-5, April 2025.
    Full text in Acris/Aaltodoc: https://urn.fi/URN:NBN:fi:aalto-202506195059
    DOI: 10.1109/ICASSP49660.2025.10889433 View at publisher
  • [Publication 4]: X. Wang, E. Ollila, and S. A. Vorobyov. Robust activity detection for massive random access. IEEE Transactions on Signal Processing, vol. 73, pp. 3513-3527, Aug 2025.
    Full text in Acris/Aaltodoc: https://urn.fi/URN:NBN:fi:aalto-202510228499
    DOI: 10.1109/TSP.2025.3597931 View at publisher
  • [Publication 5]: X. Wang, E. Ollila, and S. A. Vorobyov. Nonnegative structured Kruskal tensor regression. In Proc. 9th Workshop Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Herradura, Costa Rica, pp. 441-445, December 2023.
    Full text in Acris/Aaltodoc: https://urn.fi/URN:NBN:fi:aalto-202403062571
    DOI: 10.1109/CAMSAP58249.2023.10403474 View at publisher
  • [Publication 6]: X. Wang, E. Ollila, S. A. Vorobyov, and A. Mian. Generalized nonnegative structured Kruskal tensor regression. Signal Processing, 110338, Mar. 2026.
    Full text in Acris/Aaltodoc: https://urn.fi/URN:NBN:fi:aalto-202510298619
    DOI: 10.1016/j.sigpro.2025.110338 View at publisher

Citation

Permanent link to this item

https://urn.fi/URN:ISBN:978-952-64-2878-9

Collections

[diss] Sähkötekniikan korkeakoulu / ELEC